Complete AI Training
Sign inGet my AI kit

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

AI agent for chief digital officers

Data Product Adoption Review Agent

A leaner data product catalog where unused items are retired and good ones get support

DecisionsExecutives and strategyManagement
See how it worksGet access
Data Product Adoption Review Agent: what goes in, what the agent does and what you get

What it does

Data teams build reports that nobody opens after launch, and each one still needs upkeep. Every quarter this agent pulls usage logs, storage and compute costs, and support tickets for every dashboard, data set and model. It groups each one as healthy, low use, duplicate or unused. Before calling something unused, it checks whether it feeds another product, so nothing upstream is retired by mistake. If a dependency exists, it moves the item back to review. It drafts notices to owners proposing archive, merge or promotion, and tracks replies. It decides between archive and merge by checking overlap with other products. The CDO approves any archive, and owners can object. Edge case: a report used only at year end is kept if it was opened in the last annual cycle.

How it works

Follow the arrows from top to bottom. The orange dashed arrow is the loop: when a check fails, the agent goes back and tries again.

Start and resultWhat it doesA check on its own workWaits for your OKGoes back and retries
Yes, continueYes, continueApprovedNoNo 1 STARTS WHEN Quarter ends 2 USES A TOOL Pull usage, cost and ticket data per product 3 DOES Group products as healthy, low use, duplicate orunused 4 USES A TOOL Check lineage for downstream dependencies 5 CHECKS THE RESULT Is each archive candidate free of downstream use? If not: move it back to low use and note the dependency.Back to step 3. 6 DOES Draft owner notices with archive, merge or keepproposals 7 CHECKS THE RESULT Did each owner reply within 14 days? If not: send one reminder, then list it for the CDO.Back to step 6. 8 YOU APPROVE CDO approves archives and merges 9 RESULT Updated catalog and savings estimate
Read the steps as a list
  1. Quarter ends
  2. Pull usage, cost and ticket data per product
  3. Group products as healthy, low use, duplicate or unused
  4. Check lineage for downstream dependencies
  5. Is each archive candidate free of downstream use?If not: move it back to low use and note the dependency. Back to step 3.
  6. Draft owner notices with archive, merge or keep proposals
  7. Did each owner reply within 14 days?If not: send one reminder, then list it for the CDO. Back to step 6.
  8. CDO approves archives and mergesThe agent waits here for your OK.
  9. Updated catalog and savings estimate

How it decides

Items with no opens in 90 days and no downstream use are archive candidates; items with over 70 percent field overlap are merge candidates.

  • No opens in 90 days and no downstream use means archive candidate
  • Over 70 percent field overlap means merge candidate
  • Year-end reports are kept if used in the last annual cycle
  • Owner objection with a reason keeps the item for one more quarter

Make it yours

Every agent is a starting point. You choose these settings for your own situation.

  • Unused window (default 90 days)
  • Overlap threshold for merges (default 70 percent)
  • Owner reply window (default 14 days)
  • Products in scope (default dashboards and data sets)

What keeps you in control

It always asks you first

  • CDO approves archive and merge
  • Owner can object before archive

Hard limits

  • Never deletes data; archive is reversible
  • Never archives without CDO approval

It stops when

  • Done: catalog updated
  • Stop: lineage data is incomplete for a domain

Set it up

We guide you through the set-up, step by step

Members get the full set-up guide for this agent. No technical skills needed: you copy, paste and upload.

10 minto set it up in your AI
5 AIsChatGPT, Claude, Copilot, Gemini, Grok
  • One set of instructions to paste into your AI, with the clicks for ChatGPT, Claude, Microsoft 365 Copilot, Gemini and Grok
  • The agent then walks you through connecting your own data, one source at a time
  • A downloadable copy with the flow chart, the rules and the full guide
Get access to this agent

An example run

What happensIn the Q2 review the agent found 412 dashboards; 96 had no opens in 90 days. Lineage showed 11 of those fed scheduled exports, so they moved back to low use. Owners of 61 agreed to archive, 9 objected with reasons, and 15 did not reply after a reminder. The CDO approved archiving 61 and merging two sales dashboards.

More agents for chief digital officers

Decisions · IT and development

Blockchain Use Case Feasibility Screen Agent

A fair, documented screen of a blockchain proposal with a clear recommendation

10 steps2 checks6 jobs
Compliance · Executives and strategy

Data Retention and Deletion Schedule Agent

Data is deleted when the policy says, with proof, and nothing under hold or in use is touched.

10 steps2 checks6 jobs
Compliance · Risk management

Data Vendor and Third-Party Sharing Review Agent

Every vendor that receives data has a current agreement and review.

11 steps2 checks9 jobs
Compliance · Executives and strategy

Customer Data Consent and Preference Sync Agent

Consent and preferences match in every system, with unresolved records listed.

11 steps2 checks5 jobs